java APIs for xml --------dom(1)

# Java API for XML Processing (JAXP)
# Study Note of JAVA Tutorial

Document Object Model APIs

　　node 接口是文档对象模型的主要类型，它代表了文档树中的单个节点。Node 有很多子类(接口),具体属性如下表：

node(subclass)	Named Constant	nodeName	nodeValue	attributes
Attr	Node.ATTRIBUTE_NODE	same as Attr.name	same as Attr.value	null
CDATASection	Node.CDATA_SECTION_NODE	"#cdata-section"	same as CharacterData.data, the content of the CDATA Section	null
Comment	Node.COMMENT_NODE	"#comment"	same as CharacterData.data, the content of the comment	null
Document	Node.DOCUMENT_NODE	"#document"	null	null
DocumentFragment	Node.DOCUMENT_FRAGMENT_NODE	"#document-fragment"	null	null
DocumentType	Node.DOCUMENT_TYPE_NODE	same as DocumentType.name	null	null
Element	Node.ELEMENT_NODE	same as Element.tagName	null	NamedNodeMap
Entity	Node.ENTITY_NODE	entity name	null	null
EntityReference	Node.ENTITY_REFERENCE_NODE	name of entity referenced	null	null
Notation	Node.NOTATION_NODE	notation name	null	null
ProcessingInstruction	Node.PROCESSING_INSTRUCTION_NODE	same as ProcessingInstruction.target	same as ProcessingInstruction.data	null
Text	Node.TEXT_NODE	"#text"	same as CharacterData.data, the content of the text node	null

 

节点类型	描述	子元素
Document	表示整个文档（DOM 树的根节点）	Element (max. one) ProcessingInstruction Comment DocumentType
DocumentFragment	表示轻量级的 Document 对象，其中容纳了一部分文档。	ProcessingInstruction Comment Text CDATASection EntityReference
DocumentType	向为文档定义的实体提供接口。	None
ProcessingInstruction	表示处理指令。	None
EntityReference	表示实体引用元素。	ProcessingInstruction Comment Text CDATASection EntityReference
Element	表示 element（元素）元素	Text Comment ProcessingInstruction CDATASection EntityReference
Attr	表示属性。	Text EntityReference
Text	表示元素或属性中的文本内容。	None
CDATASection	表示文档中的 CDATA 区段（文本不会被解析器解析）	None
Comment	表示注释。	None
Entity	表示实体。	ProcessingInstruction Comment Text CDATASection EntityReference
Notation	表示在 DTD 中声明的符号。	None

把xml dom parsing 分为3个步骤：

1. Instantiate the Factory and Set Properties

2. Get a Parser and set Error Handler

3. Parse the File and Get DOM Tree

domparser 类实现了上面三个步骤，代码如下：

package dom;

import java.io.File;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;

import org.w3c.dom.Document;
import org.xml.sax.ErrorHandler;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;

public class domparser {
    static final String outputEncoding = "UTF-8";
    
    /* Constants used for XML validation */
    static final String JAXP_SCHEMA_LANGUAGE = "http://java.sun.com/xml/jaxp/properties/schemaLanguage";
    static final String W3C_XML_SCHEMA = "http://www.w3.org/2001/XMLSchema";
    static final String JAXP_SCHEMA_SOURCE = "http://java.sun.com/xml/jaxp/properties/schemaSource";
        
    public static void main(String[] args) throws ParserConfigurationException, SAXException, IOException {

        /*
         *  dtdValidate          : DTD validation, if true, do validation 
         *  xsdValidate          : W3C XML Schema validation, if true, do validation 
         *  schemaSource         : schema source XSD file
         *  ignoreWhitespace     : if true, ignore white space
         *  ignoreComments       : if true, ignore comments
         *  putCDATAIntoText     : if true, put CDATA into Text nodes
         *  createEntityRefs     : create EntityReference nodes
         */
        String filename = "/sandbox/javatest/data.xml";
        boolean dtdValidate = false;
        boolean xsdValidate = false;
        String schemaSource = null;
        boolean ignoreWhitespace = true;
        boolean ignoreComments = false;
        boolean putCDATAIntoText = false;
        boolean createEntityRefs = false;

        /**  Step 1: create a DocumentBuilderFactory and configure it */
        DocumentBuilderFactory dbf =DocumentBuilderFactory.newInstance();
        /*
         *  Set namespaceAware to true to get a DOM Level 2 tree with nodes containing NameSapce information.
         */
        dbf.setNamespaceAware(true);
        
        // Set the validation mode: no validation, DTD validation, or XSD validation
        dbf.setValidating(dtdValidate || xsdValidate);
        if (xsdValidate) {
            try {
                dbf.setAttribute(JAXP_SCHEMA_LANGUAGE, W3C_XML_SCHEMA);
            } catch (IllegalArgumentException x) {
                // This can happen if the parser does not support JAXP 1.2
                System.err.println(
                    "Error: JAXP DocumentBuilderFactory attribute not recognized: "
                    + JAXP_SCHEMA_LANGUAGE);
                System.err.println(
                    "Check to see if parser conforms to JAXP 1.2 spec.");
                System.exit(1);
            }
        }

        // Set the schema source.
        if (schemaSource != null) {
            dbf.setAttribute(JAXP_SCHEMA_SOURCE, new File(schemaSource));
        }
        
        // Optional: set various configuration options
        dbf.setIgnoringComments(ignoreComments);
        dbf.setIgnoringElementContentWhitespace(ignoreWhitespace);
        dbf.setCoalescing(putCDATAIntoText);
        // The opposite of creating entity reference nodes is expanding them inline
        dbf.setExpandEntityReferences(!createEntityRefs);

        /** Step 2: create a DocumentBuilder that satisfies the constraints specified by the DocumentBuilderFactory*/
        DocumentBuilder db = dbf.newDocumentBuilder();
        // Set an ErrorHandler before parsing
        OutputStreamWriter errorWriter = new OutputStreamWriter(System.err, outputEncoding);
        db.setErrorHandler( new MyErrorHandler(new PrintWriter(errorWriter, true)));

        /** Step 3: parse the input file and handle dom tree*/
        Document doc = db.parse(new File(filename));

        // handling the DOM tree
        OutputStreamWriter outWriter = new OutputStreamWriter(System.out, outputEncoding);
        new domecho(new PrintWriter(outWriter, true)).echo(doc);
    }
    private static class MyErrorHandler implements ErrorHandler {
        /** Error handler output goes here */
        private PrintWriter out;

        MyErrorHandler(PrintWriter out) {
            this.out = out;
        }

        /**
         * Returns a string describing parse exception details
         */
        private String getParseExceptionInfo(SAXParseException spe) {
            String systemId = spe.getSystemId();
            if (systemId == null) {
                systemId = "null";
            }
            String info = "URI=" + systemId +
                " Line=" + spe.getLineNumber() +
                ": " + spe.getMessage();
            return info;
        }

        // The following methods are standard SAX ErrorHandler methods.
        // See SAX documentation for more info.

        public void warning(SAXParseException spe) throws SAXException {
            out.println("Warning: " + getParseExceptionInfo(spe));
        }
        
        public void error(SAXParseException spe) throws SAXException {
            String message = "Error: " + getParseExceptionInfo(spe);
            throw new SAXException(message);
        }

        public void fatalError(SAXParseException spe) throws SAXException {
            String message = "Fatal Error: " + getParseExceptionInfo(spe);
            throw new SAXException(message);
        }
    }

}

View Code

然后是DOM Tree 的处理部分,这里只是把node 信息输出，实现该功能的是domecho类，代码如下：

package dom;

import java.io.PrintWriter;

import org.w3c.dom.DocumentType;
import org.w3c.dom.Entity;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;

public class domecho {
    private PrintWriter out;

    /** Indent level */
    private int indent = 0;
    
    /** Indentation will be in multiples of basicIndent  */
    private final String basicIndent = "  ";
    
    domecho(PrintWriter out) {
        this.out = out;
    }

    /**
     * Echo common attributes of a DOM2 Node and terminate output with an
     * EOL character.
     */
    private void printlnCommon(Node n) {
        out.print(" nodeName=\"" + n.getNodeName() + "\"");

        String val = n.getNamespaceURI();
        if (val != null) {
            out.print(" uri=\"" + val + "\"");
        }

        val = n.getPrefix();
        if (val != null) {
            out.print(" pre=\"" + val + "\"");
        }

        val = n.getLocalName();
        if (val != null) {
            out.print(" local=\"" + val + "\"");
        }

        val = n.getNodeValue();
        if (val != null) {
            out.print(" nodeValue=");
            if (val.trim().equals("")) {
                // Whitespace
                out.print("[WS]");
            } else {
                out.print("\"" + n.getNodeValue() + "\"");
            }
        }
        out.println();
    }

    /**
     * Indent to the current level in multiples of basicIndent
     */
    private void outputIndentation() {
        for (int i = 0; i < indent; i++) {
            out.print(basicIndent);
        }
    }

    /**
     * Recursive routine to print out DOM tree nodes
     */
    public void echo(Node n) {
        // Indent to the current level before printing anything
        outputIndentation();

        int type = n.getNodeType();
        switch (type) {
        case Node.ATTRIBUTE_NODE:
            out.print("ATTR:");
            printlnCommon(n);
            break;
        case Node.CDATA_SECTION_NODE:
            out.print("CDATA:");
            printlnCommon(n);
            break;
        case Node.COMMENT_NODE:
            out.print("COMM:");
            printlnCommon(n);
            break;
        case Node.DOCUMENT_FRAGMENT_NODE:
            out.print("DOC_FRAG:");
            printlnCommon(n);
            break;
        case Node.DOCUMENT_NODE:
            out.print("DOC:");
            printlnCommon(n);
            break;
        case Node.DOCUMENT_TYPE_NODE:
            out.print("DOC_TYPE:");
            printlnCommon(n);

            // Print entities if any
            NamedNodeMap nodeMap = ((DocumentType)n).getEntities();
            indent += 2;
            for (int i = 0; i < nodeMap.getLength(); i++) {
                Entity entity = (Entity)nodeMap.item(i);
                echo(entity);
            }
            indent -= 2;
            break;
        case Node.ELEMENT_NODE:
            out.print("ELEM:");
            printlnCommon(n);

            /* 
             * Print attributes if any.  
             * Note: element attributes are not children of ELEMENT_NODEs .
             * But are properties of their associated ELEMENT_NODE.  
             * For this reason, they are printed with 2x the indent level to indicate this.
             */
            NamedNodeMap atts = n.getAttributes();
            indent += 2;
            for (int i = 0; i < atts.getLength(); i++) {
                Node att = atts.item(i);
                echo(att);
            }
            indent -= 2;
            break;
        case Node.ENTITY_NODE:
            out.print("ENT:");
            printlnCommon(n);
            break;
        case Node.ENTITY_REFERENCE_NODE:
            out.print("ENT_REF:");
            printlnCommon(n);
            break;
        case Node.NOTATION_NODE:
            out.print("NOTATION:");
            printlnCommon(n);
            break;
        case Node.PROCESSING_INSTRUCTION_NODE:
            out.print("PROC_INST:");
            printlnCommon(n);
            break;
        case Node.TEXT_NODE:
            out.print("TEXT:");
            printlnCommon(n);
            break;
        default:
            out.print("UNSUPPORTED NODE: " + type);
            printlnCommon(n);
            break;
        }

        // Print children if any
        indent++;
        for (Node child = n.getFirstChild(); child != null;
             child = child.getNextSibling()) {
            echo(child);
        }
        indent--;
    }
}

View Code

 

转载于:https://www.cnblogs.com/ct-blog/p/5500444.html